TokenBingeby JoDevelop
All model prices
Mistral AI

ministral-8b-latest

Official price

Model overview

The middle step of the lightweight line costs 0.15 in both directions, half again the 0.1 of the 3B variant and 25 percent below the 0.2 of the 14B one. Its input rate matches mistral-small-latest exactly, which makes that comparison unusually clean: the same 0.15 to send, then 0.15 against 0.6 to receive, four times less on generation in exchange for a model declaring agentic and lightweight capabilities but neither multimodal nor multilingual support. That boundary decides it, and text-only automation of moderate complexity belongs on ministral-8b-latest, while anything involving images or a spread of languages has to move up despite paying four times more per generated token.

Billing conditions: Standard API price. Mistral publishes a 90% discount for cached input; cache-write prices are not published separately.

Context window
0 tokens
Knowledge cutoff
Price last verified
First observed

Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.

Capabilities and formats

  • text
  • agentic
  • lightweight

Performance references

No comparable benchmark data is currently available.

PRICE EVOLUTION

Price history

Original observation and every later change, including any change of price source.

  1. Original observed priceOfficial price
    Input: $0.15Cached input: $0.015Cache write 5m: Cache write 1h: Output: $0.15